修改esmm生产项目的print

eda/esmm/Model_pipline/feature.py

@@ -57,11 +57,12 @@ def get_data():
     # print(df.head(2)
     print("before")
     print(df.shape)
-    print("after")
     df = df.drop_duplicates()
     df = df.drop_duplicates(["ucity_id", "clevel2_id", "ccity_name", "device_type", "manufacturer",
                              "channel", "top", "time", "stat_date","app_list"])
 
+    print("after")
+    print(df.shape)
     app_list_number,app_list_map = multi_hot(df,"app_list",1)
     level2_number,level2_map = multi_hot(df,"clevel2_id",1+app_list_number)
     # df["app_list"] = df["app_list"].fillna("lost_na")

tensnsorflow/es/feature.py

@@ -80,10 +80,7 @@ def get_data():
     print(df.shape)
 
     df = df.drop_duplicates(["ucity_id", "clevel2_id", "ccity_name", "device_type", "manufacturer",
-                             "channel", "top", "time", "stat_date","app_list"])
-
-    # df = df.drop_duplicates(["ucity_id", "clevel2_id", "ccity_name", "device_type", "manufacturer",
-    #                          "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
+                             "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
     print("去重后样本数量:",df.shape)
 
     app_list_number,app_list_map = multi_hot(df,"app_list",2)